Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies

Emanuel Laude, Thomas Möllenhoff, Michael Moeller, Jan Lellmann, Daniel Cremers

Abstract

Convex relaxations of multilabel problems have been demonstrated to produce provably optimal or near-optimal solutions to a variety of computer vision problems. Yet, they are of limited practical use as they require a fine discretization of the label space, entailing a huge demand in memory and runtime. In this work, we propose the first sublabel accurate convex relaxation for vectorial multilabel problems. Our key idea is to approximate the dataterm in a piecewise convex (rather than piecewise linear) manner. As a result we have a more faithful approximation of the original cost function that provides a meaningful interpretation for fractional solutions of the relaxed convex problem.
OriginalspracheEnglisch
TitelComputer Vision – ECCV 2016
Redakteure/-innenBastian Leibe, Jiri Matas, Nicu Sebe, Max Welling
Seitenumfang14
Band9905
Herausgeber (Verlag)Springer International Publishing
Erscheinungsdatum17.09.2016
Seiten614-627
ISBN (Print)978-3-319-46447-3
ISBN (elektronisch)978-3-319-46448-0
DOIs
PublikationsstatusVeröffentlicht - 17.09.2016
Veranstaltung14th European Conference on Computer Vision - Amsterdam, Niederlande
Dauer: 11.10.201614.10.2016
Konferenznummer: Part I

Fingerprint

Untersuchen Sie die Forschungsthemen von „Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren